Dissertation · 2026 · Open access

Privacy in Large Language Models: a unified study of threats, defenses, and clinical applications

MICHELE MIRANDA

IRIS Research product catalog (Sapienza University of Rome) · Published 28 September 2026

Open full textCite this paper

In brief

“Privacy in Large Language Models: a unified study of threats, defenses, and clinical applications” is a 2026 dissertation by MICHELE MIRANDA, published in IRIS Research product catalog (Sapienza University of Rome). OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY-NC-SA licence: the full text is free to read at IRIS Research product catalog (Sapienza University of Rome).

Citations
0
Authors
1

Abstract

Artificial Intelligence has progressively shifted from hand-crafted, rule-based systems to data-driven models that learn general patterns from large corpora. In Natural Language Processing (NLP), this evolution has culminated in Large Language Models (LLMs): high-capacity neural models that, by combining large-scale pretraining with modern adaptation techniques, can follow instructions, generalize across tasks, and generate fluent text in many settings. In just a few years, LLMs have become a widely used interface for interacting with information and services, with chat-style assistants turning language into a practical programming and control medium for end users. This rapid adoption has made privacy a central concern. LLMs are trained on vast amounts of text, may be adapted to domain-specific corpora, and are routinely prompted with user-provided context. These choices create multiple avenues for unintended disclosure: models can memorize rare or sensitive sequences and may reproduce identifying details during generation. Adversaries can also probe models through inference-time interactions to extract information. At the same time, mitigating privacy risks is not merely a matter of data removal: protective interventions often interact with model quality, domain utility, and the practical constraints of deployment in resource-limited or regulated environments. This thesis studies privacy-preserving LLMs by combining a unifying perspective on threats with empirical investigations of defenses, with particular emphasis on Differential Privacy (DP) as a prin- cipled tool for limiting the influence of any single training record on a model’s behavior. DP offers a formal notion of protection with explicit parameters and composition properties, but its practical application requires careful modeling choices and accounting procedures that can materially affect both privacy and utility. The work is organized around three complementary directions. First, we provide a structured survey of privacy risks and mitigation strategies for LLMs, focusing in depth on DP-based ap- proaches and on recurring methodological issues in measuring privacy-utility trade-offs. Second, motivated by the high stakes of healthcare text, we investigate LLM-based de-identification for clinical notes in multilingual contexts through case studies on Italian and Dutch clinical narratives, where we comparatively evaluate manual anonymization, NER-based pipelines, and DP-based tech- niques under a consistent evaluation framework. Third, we examine privacy risks that arise specif- ically from prompting by introducing and studying a membership inference attack that targets in- context demonstrations, where the adversary aims to infer whether a candidate record was included among the examples used to condition generation. In addition, we document a DP-ICL pipeline for synthetic clinical text generation developed in the context of DataTools4Heart, as a building block towards CardioSynth, a planned open synthetic cardiology dataset containing…

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

MIRANDA, M. (2026). Privacy in Large Language Models: a unified study of threats, defenses, and clinical applications. IRIS Research product catalog (Sapienza University of Rome). https://hdl.handle.net/11573/1776320

MLA 9

MIRANDA, MICHELE. “Privacy in Large Language Models: a unified study of threats, defenses, and clinical applications.” IRIS Research product catalog (Sapienza University of Rome), 2026. https://hdl.handle.net/11573/1776320.

Chicago

MIRANDA, MICHELE. 2026. “Privacy in Large Language Models: a unified study of threats, defenses, and clinical applications.” IRIS Research product catalog (Sapienza University of Rome). https://hdl.handle.net/11573/1776320.

Harvard

MIRANDA, M. (2026) ‘Privacy in Large Language Models: a unified study of threats, defenses, and clinical applications’, IRIS Research product catalog (Sapienza University of Rome). Available at: https://hdl.handle.net/11573/1776320.

IEEE

M. MIRANDA, “Privacy in Large Language Models: a unified study of threats, defenses, and clinical applications,” IRIS Research product catalog (Sapienza University of Rome), 2026.

BibTeX

@phdthesis{miranda2026privacy,
  title     = {{Privacy in Large Language Models: a unified study of threats, defenses, and clinical applications}},
  author    = {MIRANDA, MICHELE},
  year      = {2026},
  url       = {https://hdl.handle.net/11573/1776320}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • large language models
  • privacy
  • differential privacy
  • privacy-utility trade-off
  • clinical notes
  • membership inference attacks
  • in-context learning
  • adversarial prompting

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

MIRANDA, M. (2026). Privacy in Large Language Models: a unified study of threats, defenses, and clinical applications. IRIS Research product catalog (Sapienza University of Rome). https://hdl.handle.net/11573/1776320

How many times has this paper been cited?

0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at IRIS Research product catalog (Sapienza University of Rome): sign in and open the full text from this page.

Who wrote this paper?

MICHELE MIRANDA.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.